相关论文: Long-frame-shift Neural Speech Phase Prediction wi…

Recently, progressive learning has shown its capacity to improve speech quality and speech intelligibility when it is combined with deep neural network (DNN) and long short-term memory (LSTM) based monaural speech enhancement algorithms,…

Speech enhancement techniques based on deep learning have brought significant improvement on speech quality and intelligibility. Nevertheless, a large gain in speech quality measured by objective metrics, such as perceptual evaluation of…

Recent deep learning approaches have achieved impressive performance on speech enhancement and separation tasks. However, these approaches have not been investigated for separating mixtures of arbitrary sounds of different types, a task we…

Segments that span contiguous parts of inputs, such as phonemes in speech, named entities in sentences, actions in videos, occur frequently in sequence prediction problems. Segmental models, a class of models that explicitly hypothesizes…

Multi-channel speech enhancement extracts speech using multiple microphones that capture spatial cues. Effectively utilizing directional information is key for multi-channel enhancement. Deep learning shows great potential on multi-channel…

Speech intelligibility can be degraded due to multiple factors, such as noisy environments, technical difficulties or biological conditions. This work is focused on the development of an automatic non-intrusive system for predicting the…

In this paper, we propose a transformer-based architecture, called two-stage transformer neural network (TSTNN) for end-to-end speech denoising in the time domain. The proposed model is composed of an encoder, a two-stage transformer module…

Nonnegative Matrix Factorization (NMF) is a powerful tool for decomposing mixtures of audio signals in the Time-Frequency (TF) domain. In applications such as source separation, the phase recovery for each extracted component is a major…

Vision-and-language navigation (VLN) is a crucial but challenging cross-modal navigation task. One powerful technique to enhance the generalization performance in VLN is the use of an independent speaker model to provide pseudo instructions…

The Short-Time Fourier Transform (STFT) has been a staple of signal processing, often being the first step for many audio tasks. A very familiar process when using the STFT is the search for the best STFT parameters, as they often have…

This paper addresses the problem of speech separation and enhancement from multichannel convolutive and noisy mixtures, \emph{assuming known mixing filters}. We propose to perform the speech separation and enhancement task in the short-time…

While deep reinforcement learning (RL) has been demonstrated effective in solving complex control tasks, sample efficiency remains a key challenge due to the large amounts of data required for remarkable performance. Existing research…

Speaker localization using microphone arrays depends on accurate time delay estimation techniques. For decades, methods based on the generalized cross correlation with phase transform (GCC-PHAT) have been widely adopted for this purpose.…

In multi-temporal SAR interferometry (MT-InSAR), persistent scatterer (PS) pixels are used to estimate geophysical parameters, essentially deformation. Conventionally, PS pixels are selected on the basis of the estimated noise present in…

Multi-frame algorithms for single-microphone speech enhancement, e.g., the multi-frame minimum variance distortionless response (MFMVDR) filter, are able to exploit speech correlation across adjacent time frames in the short-time Fourier…

Statistical signal processing based speech enhancement methods adopt expert knowledge to design the statistical models and linear filters, which is complementary to the deep neural network (DNN) based methods which are data-driven. In this…

This paper addresses the problem of under-determinded speech source separation from multichannel microphone singals, i.e. the convolutive mixtures of multiple sources. The time-domain signals are first transformed to the short-time Fourier…

Accurate alignment of dysfluent speech with intended text is crucial for automating the diagnosis of neurodegenerative speech disorders. Traditional methods often fail to model phoneme similarities effectively, limiting their performance.…

Neural vocoders are central to speech synthesis; despite their success, most still suffer from limited prosody modeling and inaccurate phase reconstruction. We propose a vocoder that introduces prosody-guided harmonic attention to enhance…

Various informative factors mixed in speech signals, leading to great difficulty when decoding any of the factors. An intuitive idea is to factorize each speech frame into individual informative factors, though it turns out to be highly…